2022

PhysDiff: Physics-Guided Human Motion Diffusion Model

Yuan, Ye, Song, Jiaming, Iqbal, Umar et al.

Understand

Denoising diffusion models hold great promise for generating diverse and realistic human motions.

  • However, existing motion diffusion models largely disregard the laws of physics in the diffusion process and often generate physically-implausible motions with pronounced artifacts such as floating, foot sliding, and ground penetration.
  • This seriously impacts the quality of generated motions and limits their real-world application.
  • To address this issue, we present a novel physics-guided motion diffusion model (PhysDiff), which incorporates physical constraints into the diffusion process.

Reading the bibliography…